【摘要】 越来越多的高性能网络通过电路交换或MPLS/GMPLS技术提供专用信道,支持大数据传输。为带宽预留服务开发有效的调度算法已成为提高网络资源利用率和满足应用用户传输要求的关键任务。高性能网络中即时带宽的研究集中关注在单次性能,本文对于即时调度中的周期性能优化,考虑一个新的问题:即时调度中的周期调度最大化问题。本文证明此问题是NP问题,针对此问题提出并实现了一个启发式算法:FBMHA,对FBMHA与Greed-MSR算法进行了大量的实验进行评估。实验结果表明,FBMHA算法相比于Greed-MSR算法在成功率和传输数据量方面有大的提升,表现出了FBMHA算法的优越性。更多还原

【Abstract】 More and more high-performance networks provide dedicated channels through circuit switching or MPLS/GMPLS technology to support big data transmissions. Developing effective scheduling algorithms for bandwidth reservation services has become a key task to improve network resource utilization and meet application user transmission requirements. The research on real-time bandwidth in high-performance networks focuses on single-time performance. This paper proposes a new problem for the optimization of periodic performance in real-time scheduling: the problem of maximizing the number of periodic scheduling in real-time scheduling. This paper proves that this problem is an NP problem. A heuristic algorithm is proposed and implemented for this problem: FBMHA, and a lot of experiments are carried out on the FBMHA and Greed-MSR algorithms. The experimental results show that the FBMHA algorithm has a significant improvement in the success rate and the amount of transmitted data compared to the Greed-MSR algorithm, showing the superiority of the FBMHA algorithm.更多还原